A method, device, equipment and storage medium for evaluating power demand response potential

Abstract

The present invention discloses a method, device, equipment and storage medium for evaluating the potential of power demand response. The method comprises: determining the most similar historical day that matches the target day according to similar day matching factors; obtaining historical power consumption data, and determining the user characteristic curve of the target user on the target day and the main grid load forecast curve on the target day according to the similar power consumption data corresponding to the most similar historical day in the historical power consumption data; determining the power demand response potential of the target user on the target day according to the matching degree between the user characteristic curve and the main grid load curve, combined with the user's response willingness. The present invention realizes accurate identification of the user's demand response potential based on the comparison of the power consumption curve trends of the user and the main grid on the most similar historical day, solving the problems of difficulty in mining the user's demand-side response potential and difficulty in evaluating the effectiveness of demand response.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data analysis technology, and in particular to a method, device, equipment and storage medium for evaluating power demand response potential. Background Art

[0002] At present, electricity demand response focuses on administrative measures, mainly relying on orderly electricity consumption for constraints. Target users are mainly selected according to user type (such as industrial users, residential users, etc.), without considering the impact of user electricity consumption characteristics on the potential for demand-side response.

[0003] At present, demand-side response is mainly carried out in industrial and commercial electricity consumption, and is mainly implemented in the form of contract signing. Due to the low load, relatively poor regularity of electricity consumption, and small benefits of low-voltage users, demand response for low-voltage users is still in its infancy. In addition, in the pilot areas where low-voltage user demand response is carried out, it is difficult to accurately evaluate the effectiveness of low-voltage users' demand response based on users' daily electricity data, resulting in difficulties in settling the demand response benefits of low-voltage users. In general, the response electricity settlement first distinguishes whether the target day is a working day or a holiday. If it is a working day, the average daily electricity consumption of the previous five working days is directly extracted as the basic electricity consumption; if it is a holiday, the average daily electricity consumption of the previous five holidays is extracted as the basic electricity consumption, and the response electricity is obtained by subtracting the basic electricity consumption from the target day electricity.

[0004] The main problems with the existing demand response potential assessment are: First, the current judgment based on the user's electricity response potential is mainly based on the user's daily frozen electricity volume. When executing demand-side response, the goal is to complete the "peak shaving and valley filling" of the main grid load curve, so a specified time period is required for accurate response. Users with high daily electricity consumption may not necessarily have high electricity consumption during this time period, resulting in a misjudgment of the electricity user's response potential; Second, it is difficult to accurately evaluate the demand response effectiveness of low-voltage users based on user daily electricity data, resulting in difficulties in settling demand response benefits for low-voltage users. Summary of the invention

[0005] The present invention provides a method, device, equipment and storage medium for evaluating the power demand response potential, so as to realize accurate evaluation of the power demand response potential of power users.

[0006] In a first aspect, an embodiment of the present invention provides a method for evaluating power demand response potential, comprising:

[0007] Determine the most similar historical day that matches the target day based on similar day matching factors;

[0008] Obtain historical electricity consumption data, and determine a user characteristic curve of a target user on the target day and a main grid load forecast curve on the target day based on similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data;

[0009] According to the matching degree between the user characteristic curve and the main grid load curve and in combination with the user's response willingness, the power demand response potential of the target user on the target day is determined.

[0010] Optionally, the similar day matching factors include date factors, holiday factors and / or meteorological factors.

[0011] Optionally, determining the most similar historical day matching the target day according to the similar day matching factor includes:

[0012] Determine the date distance corresponding to each historical day according to the number of natural days between the target day and each historical day in the historical period;

[0013] According to the holiday conditions of the target day and each of the historical days, combined with the holiday distance matrix, determine the holiday distance corresponding to each of the historical days;

[0014] Determining the meteorological distance corresponding to each of the historical days according to the seasonal temperature data of the target day and each of the historical days;

[0015] The date distance, holiday distance and meteorological distance corresponding to the historical days are weighted and summed respectively to obtain the matching scores corresponding to the historical days, and the historical day with the highest matching score is selected as the most similar historical day to the target day.

[0016] Optionally, the acquiring of historical electricity consumption data, and determining a user characteristic curve of a target user on the target day and a main grid load forecast curve on the target day according to similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data, include:

[0017] Acquire historical electricity consumption data, extract electricity consumption characteristic curves corresponding to each historical day of the target user within a historical period from the historical electricity consumption data, cluster and group each of the electricity consumption characteristic curves to obtain at least one set of electricity consumption characteristic curves;

[0018] For each set of power consumption characteristic curves, extracting characteristics of each power consumption characteristic curve therein, and determining a typical characteristic curve corresponding to the power consumption characteristic curve set;

[0019] Determine a target power consumption characteristic curve set in each of the power consumption characteristic curve sets where the power consumption characteristic curve of the most similar historical day is located, and determine a typical characteristic curve corresponding to the target power consumption characteristic curve set as a user characteristic curve of the target user;

[0020] The main grid load curve of the most similar historical day is extracted from the historical electricity consumption data, and the main grid load curve is used as the main grid load forecast curve of the target day.

[0021] Optionally, determining the power demand response potential of the target user on the target day according to the matching degree between the user characteristic curve and the main grid load curve and in combination with the user response willingness includes:

[0022] Determine at least one response target time period according to the main grid load curve;

[0023] Determining the user response form potential of the target user according to the matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods;

[0024] Determining the user response power potential of the target user according to the response section power consumption of the user characteristic curve in each response target time period;

[0025] The user response intention of the target user is obtained, and the power demand response potential of the target user on the target day is determined by combining the user response form potential and the user response power potential.

[0026] Optionally, determining the user response form potential of the target user according to the curve matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods includes:

[0027] For each response target time period, extracting a user characteristic sub-curve and a main network load sub-curve of the user characteristic curve and the main network load curve in the response target time period;

[0028] Determine the Euclidean distance and curve complexity difference between the user characteristic sub-curve and the main network load sub-curve;

[0029] Determining a matching degree measurement index between the user characteristic sub-curve and the main network load sub-curve according to the Euclidean distance and the curve complexity difference;

[0030] The matching degree measurement indicators corresponding to each of the response target time periods are weighted and summed to obtain the user response form potential of the target user.

[0031] Optionally, the method further includes:

[0032] Acquire the actual power consumption curve of the target user on the target day, and determine the actual power consumption of the response section of the actual power consumption curve within the response target time period;

[0033] Determine a preset number of similar historical days that match the target day according to the similar day matching factors, and determine the response segment historical power consumption of each of the similar historical days within the response target time period;

[0034] The average of the historical electricity consumption of each response segment is taken as the settlement basic electricity consumption, and the difference between the actual electricity consumption of the response segment and the settlement basic electricity consumption is determined as the user response settlement electricity consumption.

[0035] In a second aspect, an embodiment of the present invention further provides a device for evaluating power demand response potential, the device comprising:

[0036] A most similar historical day determination module, used to determine the most similar historical day matching the target day according to similar day matching factors;

[0037] A power consumption curve determination module is used to obtain historical power consumption data, and determine the user characteristic curve of the target user on the target day and the main grid load forecast curve on the target day according to similar power consumption data corresponding to the most similar historical day in the historical power consumption data;

[0038] The response potential prediction module is used to determine the power demand response potential of the target user on the target day based on the matching degree between the user characteristic curve and the main grid load curve and the user's response willingness.

[0039] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for evaluating the potential for electric power demand response as described in any embodiment of the present invention is implemented.

[0040] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the method for evaluating the potential for electric power demand response as described in any embodiment of the present invention.

[0041] The present invention determines the most similar historical day that matches the target day according to the similar day matching factors, obtains historical electricity consumption data, determines the user characteristic curve of the target user on the target day, and the main grid load forecast curve on the target day according to the similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data, and determines the target user's power demand response potential on the target day according to the matching degree between the user characteristic curve and the main grid load curve, combined with the user's response willingness. The present invention realizes accurate identification of the user's demand response potential based on the comparison of the power consumption curve trend of the user and the main grid on the most similar historical day, solving the problem of difficulty in mining the user's demand-side response potential and difficulty in evaluating the effectiveness of demand response. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a method for evaluating power demand response potential provided by Embodiment 1 of the present invention;

[0043] Figure 2a It is a schematic diagram of the principle of a method for evaluating the potential of power demand response provided by an embodiment of the present invention;

[0044] Figure 2b is another principle schematic diagram of a method for evaluating power demand response potential provided by an embodiment of the present invention;

[0045] Figure 2c It is another principle schematic diagram of a method for evaluating power demand response potential provided by an embodiment of the present invention;

[0046] Figure 3 This is a structural block diagram of a power demand response potential assessment device provided by Embodiment 2 of the present invention;

[0047] Figure 4 It is a structural block diagram of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention are shown in the accompanying drawings, rather than all structures. In addition, the embodiments of the present invention and the features in the embodiments may be combined with each other without conflict.

[0049] Embodiment 1

[0050] Figure 1 A flow chart of a method for evaluating the power demand response potential provided in Example 1 of the present invention. This embodiment is applicable to the situation of evaluating the power demand response potential of power users. The method can be performed by a power demand response potential evaluation device, which can be implemented by software and / or hardware.

[0051] like Figure 1 As shown, the method specifically comprises the following steps:

[0052] Step 110: Determine the most similar historical day that matches the target day according to the similar day matching factors.

[0053] In this embodiment, the target user may refer to an electricity user whose electricity demand response potential needs to be predicted, and the target day may refer to a specific natural day whose electricity demand response potential needs to be predicted. The electricity demand response potential evaluation method provided in this embodiment can predict the electricity consumption of the main network and the target user on the target day, and by comparing the electricity consumption data of the two, the electricity demand response potential of the target user on the target day can be predicted. The electricity consumption of the main network and the target user on the target day can be predicted by finding the historical day that is most similar to the target day in the historical records, and the electricity consumption of the main network and the target user corresponding to the most similar historical day is used as reference data to complete the prediction of the electricity consumption.

[0054] The similar day matching factors may include date factors, holiday factors and / or weather factors.

[0055] Preferably, step 110 can be specifically implemented by the following steps:

[0056] S1101. Determine the date distance corresponding to each historical day according to the number of natural days between the target day and each historical day in the historical period.

[0057] The historical period can be the previous year of the target day, and the historical day can be any natural day within the historical period.

[0058] In this embodiment, the date factor mainly considers the natural distance between the target date and the historical date, that is, the number of natural days between the target date and the historical date. The shorter the distance, the more similar the target date and the historical date are. The distance between the two can be normalized and represented by d1. The date distance d1 can be expressed by the following formula:

[0059] d1=(|d(target day)-d(historical day)|) / 366

[0060] S1102: Determine the holiday distance corresponding to each historical day according to the holiday conditions of the target day and each historical day in combination with the holiday distance matrix.

[0061] In this embodiment, holiday factors mainly include national statutory holidays and weekends. National statutory holidays and weekends have a great impact on the grid load and user electricity consumption characteristics. This embodiment summarizes the holiday distance matrix of working days, weekends and holidays by comparing a large amount of historical data, thereby determining the holiday distance d2 between the target day and each historical day.

[0062] In a specific example, the holiday distance matrix can be defined as:

[0063] Working Days Weekends Holidays Working Days 0.0 0.8 1.0 Weekends 0.8 0.0 0.2 Holidays 1.0 0.2 0.0

[0064] S1103. Determine the meteorological distance corresponding to each historical day based on the seasonal temperature data of the target day and each historical day.

[0065] In this embodiment, the meteorological factors mainly consider the influence of temperature, fully consider the influence of temperature on the distance between similar dates, and then consider the difference between winter and non-winter, and divide the temperature distance into segments in the time dimension, into winter stage and other stages, and quantify them respectively. The meteorological distance d3 can be expressed by the following formula:

[0066]

[0067] in, and It can represent the highest perceived temperature, lowest perceived temperature and temperature difference of the target day respectively; and It can represent the highest perceived temperature, the lowest perceived temperature and the temperature difference of the historical day respectively; α can be calculated based on historical data to obtain an optimal solution, or it can be determined based on empirical values, and is generally a number between 0 and 1.

[0068] S1104. Weighted sums are taken of the date distances, holiday distances and meteorological distances corresponding to the historical days to obtain matching scores corresponding to the historical days, and the historical day with the highest matching score is selected as the most similar historical day to the target day.

[0069] In this embodiment, for each historical day, the date distance, holiday distance and meteorological distance corresponding to the historical day can be calculated through S1101-S1103, and the matching score between the historical day and the target day can be obtained by weighted summing the date distance, holiday distance and meteorological distance. Among them, the weights of the date distance, holiday distance and meteorological distance in the matching score can be pre-determined and continuously optimized based on historical experience. After obtaining the matching score of each historical day and the target day, the historical day with the highest matching score can be selected as the most similar historical day to the target day.

[0070] Step 120: Obtain historical electricity consumption data, and determine a user characteristic curve of the target user on the target day and a main grid load forecast curve on the target day based on similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data.

[0071] Among them, historical electricity consumption data may include the electricity consumption of target users in the historical period and the main grid load data. It may be the archival data of electricity users, the user's historical daily 96-point electricity consumption data and the main grid's historical 96-point load data. Before using the historical electricity consumption data for potential prediction, the historical electricity consumption data can also be processed for missing values ​​and outliers.

[0072] In this embodiment, the main grid load curve of the most similar historical day can be obtained based on the historical electricity consumption data, and the main grid load curve of the most similar historical day is used as the main grid load prediction curve of the target day. Compared with the main grid load curve, the number of electricity users is huge, and the daily curve shape of users is relatively random, so it is extremely difficult to directly predict the electricity curve of electricity users. The present invention analyzes the electricity consumption data of the previous year and uses clustering to mine the typical electricity consumption characteristic curve of users. The electricity consumption characteristic curves classified into one category are statistically eliminated to eliminate the deviation caused by the randomness of user electricity consumption, realize the extraction of user electricity consumption patterns, and obtain the user characteristic curve of the target user on the target day.

[0073] Preferably, step 120 can be specifically implemented by the following steps:

[0074] S1201. Obtain historical electricity consumption data, extract electricity consumption characteristic curves corresponding to each historical day of a target user within a historical period from the historical electricity consumption data, cluster and group each electricity consumption characteristic curve to obtain at least one set of electricity consumption characteristic curves.

[0075] Figure 2a Schematic diagram of the principle of a method for evaluating the potential of power demand response provided by an embodiment of the present invention. Figure 2a As shown in the figure, one of the sets of electricity consumption characteristic curves obtained after clustering and grouping the electricity consumption characteristic curves corresponding to each historical day of the target user in the historical period.

[0076] S1202: For each group of power consumption characteristic curve sets, extract features from each power consumption characteristic curve therein to determine a typical characteristic curve corresponding to the power consumption characteristic curve set.

[0077] Figure 2b FIG. 1 is another schematic diagram of a method for evaluating the potential of power demand response provided by an embodiment of the present invention. Figure 2a By extracting the characteristics of each power consumption characteristic curve in the Figure 2b The curve shown can be determined as Figure 2a The typical characteristic curve corresponding to the power consumption characteristic curve set in .

[0078] In this embodiment, the above process can be completed for the historical electricity consumption data of all users in the previous year, and the electricity consumption characteristic curves and typical characteristic curves containing historical dates are stored in units of user numbers to facilitate subsequent matching with the main network one by one.

[0079] S1203: Determine a target power consumption characteristic curve set containing the power consumption characteristic curve of the most similar historical day in each power consumption characteristic curve set, and determine a typical characteristic curve corresponding to the target power consumption characteristic curve set as a user characteristic curve of the target user.

[0080] Specifically, the target power consumption characteristic curve set containing the power consumption characteristic curve of the target user on the most similar historical day can be found, and the typical characteristic curve corresponding to the target power consumption characteristic curve set is determined as the user characteristic curve of the target user. In a specific example, if the power consumption characteristic curve of the target user on the most similar historical day is Figure 2a In the Figure 2b The typical characteristic curve shown is determined as the user characteristic curve of the target user.

[0081] S1204. Extract the main grid load curve of the most similar historical day from the historical electricity consumption data, and use the main grid load curve as the main grid load forecast curve for the target day.

[0082] Step 130: According to the matching degree between the user characteristic curve and the main grid load curve and in combination with the user's response willingness, the power demand response potential of the target user on the target day is determined.

[0083] In this embodiment, the user response form potential of the target user can be determined from three aspects: the user's electricity form potential identification, the power potential identification, and the user's response willingness. Specifically, the user characteristic curve and the main grid load curve are obtained by comparing step 120, and the matching degree of the two curves is quantified. Then, combined with whether the target user has a historical response record, the target user's power demand response potential on the target day is determined.

[0084] Preferably, step 130 can be specifically implemented by the following steps:

[0085] S1301. Determine at least one response target time period according to a main grid load curve.

[0086] Figure 2c is another principle schematic diagram of a method for evaluating the potential of power demand response provided by an embodiment of the present invention, such as Figure 2c As shown, the main grid load curve has a relatively obvious "trough" and two relatively obvious "peaks", one "trough" is approximately between 3:30 and 7:30, and the two "peaks" are respectively between 12:00 and 17:00, and between 19:00 and 22:00. In this embodiment, the time period where the "peak" in the main grid load curve is located can be determined as the response target time period.

[0087] S1302: Determine the user response pattern potential of the target user according to the matching degree between the user characteristic curve and the main grid load curve in each response target time period.

[0088] Furthermore, S1302 can be implemented by the following steps:

[0089] A1. For each response target time period, extract the user characteristic sub-curve and the main network load sub-curve of the user characteristic curve and the main network load curve in the response target time period.

[0090] like Figure 2c As shown, the user characteristic curve and the main grid load curve between 12:00 and 17:00 can be intercepted and determined as the user characteristic sub-curve and the main grid load sub-curve. The method for determining the user characteristic sub-curve and the main grid load sub-curve in other response target time periods is similar.

[0091] A2. Determine the Euclidean distance and curve complexity difference between the user characteristic sub-curve and the main network load sub-curve.

[0092] Specifically, we can use Euclidean distance to define the distance between two curves. The calculation method is as follows:

[0093]

[0094] The indicators for measuring the complexity of the curve can be:

[0095]

[0096] The curve complexity index can be used to measure the complexity difference between two curves to be matched:

[0097]

[0098] A3. According to the Euclidean distance and the difference in curve complexity, determine the matching index between the user characteristic sub-curve and the main network load sub-curve.

[0099] The Euclidean distance and curve complexity can be used to obtain the matching index of the two curves, and the matching index can be normalized:

[0100] CID(Q,C)=ED(Q,C)×CF(Q,C)

[0101]

[0102] LOC is the normalized matching degree measurement formula. The closer the result is to 1, the higher the matching degree of the two curves.

[0103] A4. Weighted sum of the matching degree measurement indicators corresponding to each response target time period is performed to obtain the user response form potential of the target user.

[0104] If there are multiple response target time periods on the target day, the matching degree measurement indicators corresponding to the multiple response target time periods can be weighted and summed to obtain the user response form potential of the target user.

[0105] S1303: Determine the user response power potential of the target user according to the response section power consumption of the user characteristic curve in each response target time period.

[0106] In this embodiment, the user response power potential may be to use the 75% quantile of the power in the user characteristic curve within the response target time period as the power potential value.

[0107] S1304: Obtain the user response intention of the target user, and determine the power demand response potential of the target user on the target day by combining the user response form potential and the user response power potential.

[0108] Specifically, the user response form potential, the user response quantity potential and the user response willingness can be combined to comprehensively realize the prediction of the power demand response potential, and the potential label of the target user can be generated according to the quantitative value of the power demand response potential. The potential label can be divided into high, medium and low.

[0109] The technical solution of this embodiment determines the most similar historical day that matches the target day according to the similar day matching factors, obtains historical electricity consumption data, determines the user characteristic curve of the target user on the target day, and the main grid load forecast curve on the target day according to the similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data, and determines the target user's power demand response potential on the target day according to the matching degree between the user characteristic curve and the main grid load curve, combined with the user's response willingness. The present invention realizes accurate identification of the user's demand response potential based on the comparison of the power consumption curve trend of the user and the main grid on the most similar historical day, solving the problem of difficulty in mining the user's demand-side response potential and difficulty in evaluating the effectiveness of demand response.

[0110] On the basis of the above technical solution, the power demand response potential assessment method provided by the present invention can also be used for the settlement of user response power. The specific implementation steps may include:

[0111] B1. Obtain the actual power consumption curve of the target user on the target day, and determine the actual power consumption of the response section of the actual power consumption curve within the response target time period.

[0112] B2. Determine a preset number of similar historical days that match the target day based on similar day matching factors, and determine the historical power consumption of the response section of each similar historical day within the response target time period.

[0113] B3. Take the average of the historical electricity consumption of each response segment as the basic electricity consumption for settlement, and determine the difference between the actual electricity consumption of the response segment and the basic electricity consumption for settlement as the user response settlement electricity.

[0114] Specifically, the method of determining the most similar historical day to the target day using S1101-S1104 can be used to determine a preset number of similar historical days that are most similar to the target day. The preset number can be set and adjusted in advance. In this embodiment, 7 similar historical days can be taken, and the power consumption data corresponding to the 7 similar historical days can be extracted. The power consumption within the response target time period is counted, the lowest and highest values ​​are removed, and the average power consumption of the 5 similar historical days is retained as the settlement basic power consumption. The settlement of the response power can use the actual power consumption in the response section of the target day minus the settlement basic power consumption to obtain the user's response settlement power.

[0115] Embodiment 2

[0116] The power demand response potential assessment device provided in the embodiment of the present invention can execute the power demand response potential assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 3 is a structural block diagram of a power demand response potential assessment device provided by Embodiment 2 of the present invention, such as Figure 3 As shown, the device includes: a most similar historical day determination module 210, a power consumption curve determination module 220 and a response potential prediction module 230.

[0117] The most similar historical day determination module 210 is used to determine the most similar historical day matching the target day according to the similar day matching factors;

[0118] The power consumption curve determination module 220 is used to obtain historical power consumption data, and determine the user characteristic curve of the target user on the target day and the main grid load forecast curve on the target day according to the similar power consumption data corresponding to the most similar historical day in the historical power consumption data;

[0119] The response potential prediction module 230 is used to determine the power demand response potential of the target user on the target day according to the matching degree between the user characteristic curve and the main grid load curve and the user response willingness.

[0120] The technical solution of this embodiment determines the most similar historical day that matches the target day according to the similar day matching factors, obtains historical electricity consumption data, determines the user characteristic curve of the target user on the target day, and the main grid load forecast curve on the target day according to the similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data, and determines the target user's power demand response potential on the target day according to the matching degree between the user characteristic curve and the main grid load curve, combined with the user's response willingness. The present invention realizes accurate identification of the user's demand response potential based on the comparison of the power consumption curve trend of the user and the main grid on the most similar historical day, solving the problem of difficulty in mining the user's demand-side response potential and difficulty in evaluating the effectiveness of demand response.

[0121] Optionally, the similar day matching factors include date factors, holiday factors and / or meteorological factors.

[0122] Optionally, the most similar historical day determination module 210 includes:

[0123] A date factor determination unit, used to determine the date distance corresponding to each historical day according to the number of natural days between the target day and each historical day in the historical period;

[0124] A holiday factor determination unit, configured to determine the holiday distances corresponding to the historical days according to the holiday conditions of the target day and the historical days in combination with a holiday distance matrix;

[0125] A holiday factor determination unit, used to determine the meteorological distance corresponding to each of the historical days according to the seasonal temperature data of the target day and each of the historical days;

[0126] The most similar historical day determination unit is used to weightedly sum the date distance, holiday distance and meteorological distance corresponding to the historical days, obtain the matching score corresponding to each historical day, and select the historical day with the highest matching score as the most similar historical day to the target day.

[0127] Optionally, the power consumption curve determination module 220 includes:

[0128] A power consumption characteristic curve clustering unit is used to obtain historical power consumption data, extract the power consumption characteristic curve corresponding to each historical day of the target user in the historical period from the historical power consumption data, cluster and group each of the power consumption characteristic curves, and obtain at least one set of power consumption characteristic curves;

[0129] A typical characteristic curve determination unit, configured to extract characteristics of each power characteristic curve in each power characteristic curve set, and determine a typical characteristic curve corresponding to the power characteristic curve set;

[0130] A user characteristic curve determination unit is used to determine a target power characteristic curve set where the power characteristic curve of the most similar historical day is located in each power characteristic curve set, and determine a typical characteristic curve corresponding to the target power characteristic curve set as a user characteristic curve of the target user;

[0131] The main grid load forecast curve determination unit is used to extract the main grid load curve of the most similar historical day from the historical electricity consumption data, and use the main grid load curve as the main grid load forecast curve of the target day.

[0132] Optionally, the response potential prediction module 230 includes:

[0133] a response target time period determination unit, configured to determine at least one response target time period according to the main grid load curve;

[0134] A response form potential determination unit, configured to determine the user response form potential of the target user according to the curve matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods;

[0135] a response power potential determination unit, configured to determine the user response power potential of the target user according to the response section power consumption of the user characteristic curve in each of the response target time periods;

[0136] The demand response potential determination unit is used to obtain the user response willingness of the target user, and determine the power demand response potential of the target user on the target day in combination with the user response form potential and the user response power potential.

[0137] Optionally, the response morphology potential determination unit is specifically used to:

[0138] For each response target time period, extracting a user characteristic sub-curve and a main network load sub-curve of the user characteristic curve and the main network load curve in the response target time period;

[0139] Determine the Euclidean distance and curve complexity difference between the user characteristic sub-curve and the main network load sub-curve;

[0140] Determining a matching degree measurement index between the user characteristic sub-curve and the main network load sub-curve according to the Euclidean distance and the curve complexity difference;

[0141] The matching degree measurement indicators corresponding to each of the response target time periods are weighted and summed to obtain the user response form potential of the target user.

[0142] Optionally, the device further includes a response power settlement module, and the response power settlement module is used to:

[0143] Acquire the actual power consumption curve of the target user on the target day, and determine the actual power consumption of the response section of the actual power consumption curve within the response target time period;

[0144] Determine a preset number of similar historical days that match the target day according to the similar day matching factors, and determine the response segment historical power consumption of each of the similar historical days within the response target time period;

[0145] The average of the historical electricity consumption of each response segment is taken as the settlement basic electricity consumption, and the difference between the actual electricity consumption of the response segment and the settlement basic electricity consumption is determined as the user response settlement electricity consumption.

[0146] Embodiment 3

[0147] Figure 4 A structural block diagram of a computer device provided in Embodiment 3 of the present invention is shown in FIG. Figure 4 As shown, the computer device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the computer device can be one or more. Figure 4 A processor 310 is taken as an example; the processor 310, memory 320, input device 330 and output device 340 in the computer device can be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0148] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the power demand response potential assessment method in the embodiment of the present invention (for example, the most similar historical day determination module 210, the power consumption curve determination module 220 and the response potential prediction module 230 in the power demand response potential assessment device). The processor 310 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 320, that is, realizes the above-mentioned power demand response potential assessment method.

[0149] The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include a memory remotely arranged relative to the processor 310, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0150] The input device 330 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the computer device. The output device 340 may include a display device such as a display screen.

[0151] Embodiment 4

[0152] Embodiment 4 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a method for evaluating power demand response potential when executed by a computer processor, the method comprising:

[0153] Determine the most similar historical day that matches the target day based on similar day matching factors;

[0154] Obtain historical electricity consumption data, and determine a user characteristic curve of a target user on the target day and a main grid load forecast curve on the target day based on similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data;

[0155] According to the matching degree between the user characteristic curve and the main grid load curve and in combination with the user's response willingness, the power demand response potential of the target user on the target day is determined.

[0156] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present invention, whose computer executable instructions are not limited to the method operations described above, can also execute related operations in the power demand response potential assessment method provided in any embodiment of the present invention.

[0157] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0158] It is worth noting that in the embodiment of the above-mentioned power demand response potential assessment device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0159] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for evaluating power demand response potential, characterized in that: include: Determine the most similar historical day that matches the target day based on similar day matching factors; Acquire historical electricity consumption data, and determine a user characteristic curve of a target user on the target day and a main grid load forecast curve on the target day according to similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data; According to the matching degree between the user characteristic curve and the main grid load forecast curve and in combination with the user response willingness, determining the power demand response potential of the target user on the target day; The acquiring of historical electricity consumption data, and determining the user characteristic curve of the target user on the target day and the main grid load forecast curve on the target day according to the similar electricity consumption data corresponding to the most similar historical day in the historical electricity consumption data, include: Acquire the historical electricity consumption data, extract the electricity consumption characteristic curve corresponding to each historical day of the target user in the historical period from the historical electricity consumption data, cluster and group each of the electricity consumption characteristic curves to obtain at least one set of electricity consumption characteristic curves; For each set of power consumption characteristic curves, extracting features from each of the power consumption characteristic curves therein, and determining a typical characteristic curve corresponding to the power consumption characteristic curve set; Determine a target power consumption characteristic curve set in each of the power consumption characteristic curve sets where the power consumption characteristic curve of the most similar historical day is located, and determine a typical characteristic curve corresponding to the target power consumption characteristic curve set as a user characteristic curve of the target user; Extracting the main grid load curve of the most similar historical day from the historical electricity consumption data, and using the main grid load curve as the main grid load forecast curve of the target day; The step of determining the power demand response potential of the target user on the target day based on the matching degree between the user characteristic curve and the main grid load forecast curve and the user response willingness comprises: Determine at least one response target time period according to the main grid load curve; wherein the response target time period is the time period where the peak of the main grid load curve is located; Determining the user response form potential of the target user according to the matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods; Determining the user response power potential of the target user according to the response section power consumption of the user characteristic curve in each response target time period; The user response intention of the target user is obtained, and the power demand response potential of the target user on the target day is determined by combining the user response form potential and the user response power potential.

2. The method for evaluating the potential of power demand response according to claim 1, characterized in that: The similar day matching factors include date factors, holiday factors and / or weather factors.

3. The method for evaluating the potential of power demand response according to claim 2, characterized in that: The most similar historical day matching the target day is determined based on similar day matching factors, including: Determine the date distance corresponding to each historical day according to the number of natural days between the target day and each historical day in the historical period; According to the holiday conditions of the target day and each of the historical days, combined with the holiday distance matrix, determine the holiday distance corresponding to each of the historical days; Determining the meteorological distance corresponding to each of the historical days according to the seasonal temperature data of the target day and each of the historical days; The date distance, holiday distance and meteorological distance corresponding to the historical days are weighted and summed respectively to obtain the matching scores corresponding to the historical days, and the historical day with the highest matching score is selected as the most similar historical day to the target day.

4. The method for evaluating the potential of power demand response according to claim 1, characterized in that: Determining the user response form potential of the target user according to the curve matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods includes: For each response target time period, extracting a user characteristic sub-curve and a main network load sub-curve of the user characteristic curve and the main network load curve in the response target time period; Determine the Euclidean distance and curve complexity difference between the user characteristic sub-curve and the main network load sub-curve; Determining a matching degree measurement index between the user characteristic sub-curve and the main network load sub-curve according to the Euclidean distance and the curve complexity difference; The matching degree measurement indicators corresponding to each of the response target time periods are weighted and summed to obtain the user response form potential of the target user.

5. The method for evaluating the potential of power demand response according to claim 1, characterized in that: The method further comprises: Acquire the actual power consumption curve of the target user on the target day, and determine the actual power consumption of the response section of the actual power consumption curve within the response target time period; Determine a preset number of similar historical days that match the target day according to the similar day matching factors, and determine the response segment historical power consumption of each of the similar historical days within the response target time period; The average of the historical electricity consumption of each response segment is taken as the settlement basic electricity consumption, and the difference between the actual electricity consumption of the response segment and the settlement basic electricity consumption is determined as the user response settlement electricity consumption.

6. A power demand response potential assessment device, characterized in that: include: A most similar historical day determination module, used to determine the most similar historical day matching the target day according to similar day matching factors; A power consumption curve determination module is used to obtain historical power consumption data, and determine a user characteristic curve of a target user on the target day and a main grid load forecast curve on the target day according to similar power consumption data corresponding to the most similar historical day in the historical power consumption data; A response potential prediction module, used to determine the power demand response potential of the target user on the target day according to the matching degree between the user characteristic curve and the main grid load prediction curve and the user response willingness; Wherein, the power consumption curve determination module includes: A power consumption characteristic curve clustering unit is used to obtain the historical power consumption data, extract the power consumption characteristic curve corresponding to each historical day of the target user in the historical period from the historical power consumption data, cluster and group each of the power consumption characteristic curves, and obtain at least one set of power consumption characteristic curves; A typical characteristic curve determining unit, configured to extract characteristics of each of the power characteristic curves in each power characteristic curve set, and determine a typical characteristic curve corresponding to the power characteristic curve set; A user characteristic curve determination unit is used to determine a target power characteristic curve set where the power characteristic curve of the most similar historical day is located in each power characteristic curve set, and determine a typical characteristic curve corresponding to the target power characteristic curve set as a user characteristic curve of the target user; A main grid load forecast curve determination unit, configured to extract the main grid load curve of the most similar historical day from the historical power consumption data, and use the main grid load curve as the main grid load forecast curve of the target day; Wherein, the response potential prediction module comprises: A response target time period determination unit, configured to determine at least one response target time period according to the main grid load curve; wherein the response target time period is a time period where a peak of the main grid load curve is located; A response form potential determination unit, configured to determine the user response form potential of the target user according to the curve matching degree between the user characteristic curve and the main grid load curve in each of the response target time periods; a response power potential determination unit, configured to determine the user response power potential of the target user according to the response section power consumption of the user characteristic curve in each of the response target time periods; The demand response potential determination unit is used to obtain the user response willingness of the target user, and determine the power demand response potential of the target user on the target day in combination with the user response form potential and the user response power potential.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the power demand response potential assessment method as described in any one of claims 1-5 is implemented.

8. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the power demand response potential assessment method as described in any one of claims 1 to 5.

Images